LLM Desktop Electron

LLM Desktop Electron is an API translation proxy and Electron desktop wrapper to run Claude agent tools with OpenAI or local GPU models.

LLM Desktop Electron redirects the agent layers of Claude Code and Claude Desktop to alternative backends, including OpenAI or local OpenAI-compatible engines like Ollama, llama.cpp, LM Studio, and vLLM. It features a local Node-based proxy that translates Anthropic Messages API calls to OpenAI Chat Completions or Responses endpoints. The desktop component embeds this proxy into Anthropic's Claude Desktop app run under an Electron runtime, providing a settings GUI and provider switching. The proxy translates text, tool calls, and image inputs in both directions while managing streaming, mathematical rendering adjustments, reasoning summaries, and context overflows.

LLM Desktop Electron at a glance

Best for: Software engineer
Runs on: macOS, Linux, CLI
Pricing: Free
Released: October 2026
Category: AI coding tool
Website: github.com/mkornreich/llm-desktop-electron

Key features

Translates Anthropic Messages API calls into OpenAI API formats
Supports local inference backends such as Ollama, llama.cpp, LM Studio, and vLLM
Runs Claude Desktop within a stock Electron runtime with a provider switch GUI
Executes agent turns with tool calls and automated output handling
Maps Anthropic image blocks to OpenAI image formats with vision fallbacks
Provides a process supervisor with health checks and automatic restarts
Rewrites math delimiters and manages agent context overflows automatically

Use it for

Driving the stock Claude Code CLI using an OpenAI API key
Executing Claude agent tooling on local GPUs via Ollama or llama.cpp
Using Claude Desktop on Linux or macOS with non-Anthropic model backends
Switching between third-party model providers through a cross-provider fallback chain

Companions

Tools that articles about LLM Desktop Electron recommend using with it, each with its job.

Claude — Built to work with Claude.
Claude Code — Built to work with Claude Code.
Context7 — Up-to-date API documentation for coding questions.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Make — Runs and manages Make scenarios from a conversation.
Canva — Templates for almost any design, plus AI editing in one tool

Alternatives to LLM Desktop Electron

claudecode.nvim — Adds native AI coding assistant functionality to Neovim.
Claude Code Proxy — Runs Anthropic-compatible clients with Gemini or OpenAI models.
Opencode Claude Code Plugin — Runs Claude models via the official CLI with zero token storage.
claude-mem — It shares persistent, searchable agent memory across sessions and devices.
opcode — Turns terminal Claude Code workflows into an intuitive visual interface.
Open Claude UI — Provides reverse-engineered physics constants and production-ready React components.
Claude Desktop Multiple Windows Differen — Run official and third-party AI APIs simultaneously in separate Claude Desktop windows.
Oh My ClaudeCode — Orchestrates parallel Claude, Gemini, and Codex CLI workers.
Claude Super Sidebar — It brings agent relationships, execution states, and task flows into one panel.
Claude Code Local — Runs Claude Code completely on-device without cloud limits or API keys.
Claude Code Router — It centralizes control of AI agent requests with intelligent routing and observability.
Claudish To English — It displays a local LLM-powered plain-English rewrite of each assistant message on screen.

All LLM Desktop Electron alternatives